Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Python asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative
update
游雁05f8022500ec
diff --git a/examples/industrial_data_pretraining/sense_voice/demo.py b/examples/industrial_data_pretraining/sense_voice/demo.pydeleted file mode 100644index 530399955..000000000--- a/examples/industrial_data_pretraining/sense_voice/demo.py+++ /dev/null@@ -1,28 +0,0 @@-#!/usr/bin/env python3-# -*- encoding: utf-8 -*--# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.-# MIT License (https://opensource.org/licenses/MIT)--from funasr import AutoModel--model = AutoModel(- model="/Users/zhifu/Downloads/modelscope_models/SenseVoiceModelscope",- # vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",- # vad_kwargs={"max_single_segment_time": 30000},-)---input_wav = (- "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav"-)--DecodingOptions = {- "task": ("ASR", "AED", "SER"),- "language": "auto",- "fp16": True,- "gain_event": True,- "beam_size": 5,-}--res = model.generate(input=input_wav, batch_size_s=0, DecodingOptions=DecodingOptions)-print(res)diff --git a/examples/industrial_data_pretraining/sense_voice/demo_ctc.py b/examples/industrial_data_pretraining/sense_voice/demo_ctc.pydeleted file mode 100644index a8ba7f941..000000000--- a/examples/industrial_data_pretraining/sense_voice/demo_ctc.py+++ /dev/null@@ -1,25 +0,0 @@-#!/usr/bin/env python3-# -*- encoding: utf-8 -*--# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.-# MIT License (https://opensource.org/licenses/MIT)--import sys-from funasr import AutoModel--model_dir = "/Users/zhifu/Downloads/modelscope_models/SenseVoiceCTC"-input_file = (- "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav"-)--model = AutoModel(- model=model_dir,-)--res = model.generate(- input=input_file,- cache={},- language="auto",- text_norm="woitn",-)--print(res)diff --git a/examples/industrial_data_pretraining/sense_voice/demo_fsmn.py b/examples/industrial_data_pretraining/sense_voice/demo_fsmn.pydeleted file mode 100644index ce4bdf8a2..000000000--- a/examples/industrial_data_pretraining/sense_voice/demo_fsmn.py+++ /dev/null@@ -1,28 +0,0 @@-#!/usr/bin/env python3-# -*- encoding: utf-8 -*--# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.-# MIT License (https://opensource.org/licenses/MIT)--from funasr import AutoModel--model = AutoModel(- model="/Users/zhifu/Downloads/modelscope_models/SenseVoiceModelscopeFSMN",- vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",- vad_kwargs={"max_single_segment_time": 30000},-)---input_wav = (- "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav"-)--DecodingOptions = {- "task": ("ASR", "AED", "SER"),- "language": "auto",- "fp16": True,- "gain_event": True,- "beam_size": 5,-}--res = model.generate(input=input_wav, batch_size_s=0, DecodingOptions=DecodingOptions, beam_size=5)-print(res)diff --git a/examples/industrial_data_pretraining/sense_voice/finetune.sh b/examples/industrial_data_pretraining/sense_voice/finetune.shdeleted file mode 100644index ce19eb3f8..000000000--- a/examples/industrial_data_pretraining/sense_voice/finetune.sh+++ /dev/null@@ -1,83 +0,0 @@-# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.-# MIT License (https://opensource.org/licenses/MIT)--workspace=`pwd`--# which gpu to train or finetune-export CUDA_VISIBLE_DEVICES="0"-gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')--# model_name from model_hub, or model_dir in local path--## option 1, download model automatically-model_name_or_model_dir="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"-model_name_or_model_dir="/Users/zhifu/Downloads/modelscope_models/SenseVoiceModelscope"-## option 2, download model by git-#local_path_root=${workspace}/modelscope_models-#mkdir -p ${local_path_root}/${model_name_or_model_dir}-#git clone https://www.modelscope.cn/${model_name_or_model_dir}.git ${local_path_root}/${model_name_or_model_dir}-#model_name_or_model_dir=${local_path_root}/${model_name_or_model_dir}---# data dir, which contains: train.json, val.json-data_dir="../../../data/list"--train_data="${data_dir}/train.jsonl"-val_data="${data_dir}/val.jsonl"--# generate train.jsonl and val.jsonl from wav.scp and text.txt-scp2jsonl \-++scp_file_list='["../../../data/list/train_wav.scp", "../../../data/list/train_text.txt"]' \-++data_type_list='["source", "target"]' \-++jsonl_file_out="${train_data}"--scp2jsonl \-++scp_file_list='["../../../data/list/val_wav.scp", "../../../data/list/val_text.txt"]' \-++data_type_list='["source", "target"]' \-++jsonl_file_out="${val_data}"---# exp output dir-output_dir="./outputs"-log_file="${output_dir}/log.txt"---mkdir -p ${output_dir}-echo "log_file: ${log_file}"--deepspeed_config=${workspace}/../../ds_stage1.json--DISTRIBUTED_ARGS="- --nnodes ${WORLD_SIZE:-1} \- --nproc_per_node $gpu_num \- --node_rank ${RANK:-0} \- --master_addr ${MASTER_ADDR:-127.0.0.1} \- --master_port ${MASTER_PORT:-26669}-"--echo $DISTRIBUTED_ARGS--torchrun $DISTRIBUTED_ARGS \-../../../funasr/bin/train_ds.py \-++model="${model_name_or_model_dir}" \-++train_data_set_list="${train_data}" \-++valid_data_set_list="${val_data}" \-++dataset="SenseVoiceDataset" \-++dataset_conf.IndexDSJsonl="IndexDSJsonl" \-++dataset_conf.data_split_num=1 \-++dataset_conf.batch_sampler="BatchSampler" \-++dataset_conf.batch_size=6000 \-++dataset_conf.sort_size=1024 \-++dataset_conf.batch_type="token" \-++dataset_conf.num_workers=4 \-++train_conf.max_epoch=50 \-++train_conf.log_interval=1 \-++train_conf.resume=true \-++train_conf.validate_interval=2000 \-++train_conf.save_checkpoint_interval=2000 \-++train_conf.keep_nbest_models=20 \-++train_conf.avg_nbest_model=10 \-++train_conf.use_deepspeed=false \-++train_conf.deepspeed_config=${deepspeed_config} \-++optim_conf.lr=0.0002 \-++output_dir="${output_dir}" #&> ${log_file}\ No newline at end of file